Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory

Aerial-photo interpreted inventories of forest resources, including tree species composition, are valuable in forest resource management, but are expensive to create and can be relatively inaccurate. Because of differences among tree species in their spectral properties and seasonal phenologies, it...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jay R. Malcolm, Braiden Brousseau, Trevor Jones, Sean C. Thomas
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	remote sensing multivariate tree species composition Sentinel-2 forest resource inventory random forest convolutional neural network Science Q
Acceso en línea:	https://doaj.org/article/959c4540ac5c4b2da21f2a92fdbd9c85
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:959c4540ac5c4b2da21f2a92fdbd9c85
record_format	dspace
spelling	oai:doaj.org-article:959c4540ac5c4b2da21f2a92fdbd9c852021-11-11T18:53:16ZUse of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory10.3390/rs132142972072-4292https://doaj.org/article/959c4540ac5c4b2da21f2a92fdbd9c852021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4297https://doaj.org/toc/2072-4292Aerial-photo interpreted inventories of forest resources, including tree species composition, are valuable in forest resource management, but are expensive to create and can be relatively inaccurate. Because of differences among tree species in their spectral properties and seasonal phenologies, it might be possible to improve such forest resource inventory information (FRI) by using it in concert with multispectral satellite information from multiple time periods. We used Sentinel-2 information from nine spectral bands and 12 dates within a two-year period to model multivariate percent tree species composition in >51,000 forest stands in the FRI of south-central Ontario, Canada. Accuracy of random forest (RF) and convolutional neural network (CNN) predictions were tested using species-specific basal area information from 155 0.25-ha field plots. Additionally, we created models using the Sentinel-2 information in concert with the field data and compared the accuracy of these models and the FRI-based models by use of basal areas from a second (13.7-ha) field data set. Based on average R<sup>2</sup> values across species in the two field data sets, the Sentinel-FRI models outperformed the FRI, showing 1.5- and 1.7-fold improvements relative to the FRI for RF and 2.1- and 2.2-fold improvements for CNN (mean R<sup>2</sup>: 0.141–0.169 (FRI); 0.217–0.295 (RF); 0.307–0.352 (CNN)). Models created with the field data performed even better: improvements relative to the FRI were 2.1-fold for RF and 2.8-fold for CNN (mean R<sup>2</sup>: 0.169 (FRI); 0.356 (RF); 0.469 (CNN)). As predicted, R<sup>2</sup> values between FRI- and field-trained predictions were higher than R<sup>2</sup> values with the FRI. Of the 21 tree species evaluated, 8 relatively rare species had poor models in all cases. Our multivariate approach allowed us to use more FRI stands in model creation than if we had been restricted to stands dominated by single species and allowed us to map species abundances at higher resolution. It might be possible to improve models further by use of tree stem maps and incorporation of the effects of canopy disturbances.Jay R. MalcolmBraiden BrousseauTrevor JonesSean C. ThomasMDPI AGarticleremote sensingmultivariate tree species compositionSentinel-2forest resource inventoryrandom forestconvolutional neural networkScienceQENRemote Sensing, Vol 13, Iss 4297, p 4297 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	remote sensing multivariate tree species composition Sentinel-2 forest resource inventory random forest convolutional neural network Science Q
spellingShingle	remote sensing multivariate tree species composition Sentinel-2 forest resource inventory random forest convolutional neural network Science Q Jay R. Malcolm Braiden Brousseau Trevor Jones Sean C. Thomas Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory
description	Aerial-photo interpreted inventories of forest resources, including tree species composition, are valuable in forest resource management, but are expensive to create and can be relatively inaccurate. Because of differences among tree species in their spectral properties and seasonal phenologies, it might be possible to improve such forest resource inventory information (FRI) by using it in concert with multispectral satellite information from multiple time periods. We used Sentinel-2 information from nine spectral bands and 12 dates within a two-year period to model multivariate percent tree species composition in >51,000 forest stands in the FRI of south-central Ontario, Canada. Accuracy of random forest (RF) and convolutional neural network (CNN) predictions were tested using species-specific basal area information from 155 0.25-ha field plots. Additionally, we created models using the Sentinel-2 information in concert with the field data and compared the accuracy of these models and the FRI-based models by use of basal areas from a second (13.7-ha) field data set. Based on average R<sup>2</sup> values across species in the two field data sets, the Sentinel-FRI models outperformed the FRI, showing 1.5- and 1.7-fold improvements relative to the FRI for RF and 2.1- and 2.2-fold improvements for CNN (mean R<sup>2</sup>: 0.141–0.169 (FRI); 0.217–0.295 (RF); 0.307–0.352 (CNN)). Models created with the field data performed even better: improvements relative to the FRI were 2.1-fold for RF and 2.8-fold for CNN (mean R<sup>2</sup>: 0.169 (FRI); 0.356 (RF); 0.469 (CNN)). As predicted, R<sup>2</sup> values between FRI- and field-trained predictions were higher than R<sup>2</sup> values with the FRI. Of the 21 tree species evaluated, 8 relatively rare species had poor models in all cases. Our multivariate approach allowed us to use more FRI stands in model creation than if we had been restricted to stands dominated by single species and allowed us to map species abundances at higher resolution. It might be possible to improve models further by use of tree stem maps and incorporation of the effects of canopy disturbances.
format	article
author	Jay R. Malcolm Braiden Brousseau Trevor Jones Sean C. Thomas
author_facet	Jay R. Malcolm Braiden Brousseau Trevor Jones Sean C. Thomas
author_sort	Jay R. Malcolm
title	Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory
title_short	Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory
title_full	Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory
title_fullStr	Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory
title_full_unstemmed	Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory
title_sort	use of sentinel-2 data to improve multivariate tree species composition in a forest resource inventory
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/959c4540ac5c4b2da21f2a92fdbd9c85
work_keys_str_mv	AT jayrmalcolm useofsentinel2datatoimprovemultivariatetreespeciescompositioninaforestresourceinventory AT braidenbrousseau useofsentinel2datatoimprovemultivariatetreespeciescompositioninaforestresourceinventory AT trevorjones useofsentinel2datatoimprovemultivariatetreespeciescompositioninaforestresourceinventory AT seancthomas useofsentinel2datatoimprovemultivariatetreespeciescompositioninaforestresourceinventory
_version_	1718431714412331008

Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory

Ejemplares similares